diff options
Diffstat (limited to 'projects/SelfTest/IntrospectiveTests/Xml.tests.cpp')
| -rw-r--r-- | projects/SelfTest/IntrospectiveTests/Xml.tests.cpp | 64 |
1 files changed, 33 insertions, 31 deletions
diff --git a/projects/SelfTest/IntrospectiveTests/Xml.tests.cpp b/projects/SelfTest/IntrospectiveTests/Xml.tests.cpp index c3886ab2..bf6c8602 100644 --- a/projects/SelfTest/IntrospectiveTests/Xml.tests.cpp +++ b/projects/SelfTest/IntrospectiveTests/Xml.tests.cpp @@ -40,10 +40,11 @@ TEST_CASE( "XmlEncode", "[XML]" ) { } // Thanks to Peter Bindels (dascandy) for some of the tests -TEST_CASE("XmlEncode: UTF-8", "[XML][UTF-8]") { +TEST_CASE("XmlEncode: UTF-8", "[XML][UTF-8][approvals]") { +#define ESC(lit) (char*)(lit) SECTION("Valid utf-8 strings") { - CHECK(encode(u8"Here be 👾") == u8"Here be 👾"); - CHECK(encode(u8"šš") == u8"šš"); + CHECK(encode(ESC(u8"Here be 👾")) == ESC(u8"Here be 👾")); + CHECK(encode(ESC(u8"šš")) == ESC(u8"šš")); CHECK(encode("\xDF\xBF") == "\xDF\xBF"); // 0x7FF CHECK(encode("\xE0\xA0\x80") == "\xE0\xA0\x80"); // 0x800 @@ -55,18 +56,18 @@ TEST_CASE("XmlEncode: UTF-8", "[XML][UTF-8]") { } SECTION("Invalid utf-8 strings") { SECTION("Various broken strings") { - CHECK(encode("Here \xFF be 👾") == u8"Here \\xFF be 👾"); + CHECK(encode(ESC("Here \xFF be \xF0\x9F\x91\xBE")) == ESC(u8"Here \\xFF be 👾")); CHECK(encode("\xFF") == "\\xFF"); - CHECK(encode("\xC5\xC5\xA0") == u8"\\xC5Š"); - CHECK(encode("\xF4\x90\x80\x80") == u8"\\xF4\\x90\\x80\\x80"); // 0x110000 -- out of unicode range + CHECK(encode("\xC5\xC5\xA0") == ESC(u8"\\xC5Š")); + CHECK(encode("\xF4\x90\x80\x80") == ESC(u8"\\xF4\\x90\\x80\\x80")); // 0x110000 -- out of unicode range } SECTION("Overlong encodings") { - CHECK(encode("\xC0\x80") == u8"\\xC0\\x80"); // \0 - CHECK(encode("\xF0\x80\x80\x80") == u8"\\xF0\\x80\\x80\\x80"); // Super-over-long \0 - CHECK(encode("\xC1\xBF") == u8"\\xC1\\xBF"); // ASCII char as UTF-8 (0x7F) - CHECK(encode("\xE0\x9F\xBF") == u8"\\xE0\\x9F\\xBF"); // 0x7FF - CHECK(encode("\xF0\x8F\xBF\xBF") == u8"\\xF0\\x8F\\xBF\\xBF"); // 0xFFFF + CHECK(encode("\xC0\x80") == "\\xC0\\x80"); // \0 + CHECK(encode("\xF0\x80\x80\x80") == "\\xF0\\x80\\x80\\x80"); // Super-over-long \0 + CHECK(encode("\xC1\xBF") == "\\xC1\\xBF"); // ASCII char as UTF-8 (0x7F) + CHECK(encode("\xE0\x9F\xBF") == "\\xE0\\x9F\\xBF"); // 0x7FF + CHECK(encode("\xF0\x8F\xBF\xBF") == "\\xF0\\x8F\\xBF\\xBF"); // 0xFFFF } // Note that we actually don't modify surrogate pairs, as we do not do strict checking @@ -78,35 +79,36 @@ TEST_CASE("XmlEncode: UTF-8", "[XML][UTF-8]") { } SECTION("Invalid start byte") { - CHECK(encode("\x80") == u8"\\x80"); - CHECK(encode("\x81") == u8"\\x81"); - CHECK(encode("\xBC") == u8"\\xBC"); - CHECK(encode("\xBF") == u8"\\xBF"); + CHECK(encode("\x80") == "\\x80"); + CHECK(encode("\x81") == "\\x81"); + CHECK(encode("\xBC") == "\\xBC"); + CHECK(encode("\xBF") == "\\xBF"); // Out of range - CHECK(encode("\xF5\x80\x80\x80") == u8"\\xF5\\x80\\x80\\x80"); - CHECK(encode("\xF6\x80\x80\x80") == u8"\\xF6\\x80\\x80\\x80"); - CHECK(encode("\xF7\x80\x80\x80") == u8"\\xF7\\x80\\x80\\x80"); + CHECK(encode("\xF5\x80\x80\x80") == "\\xF5\\x80\\x80\\x80"); + CHECK(encode("\xF6\x80\x80\x80") == "\\xF6\\x80\\x80\\x80"); + CHECK(encode("\xF7\x80\x80\x80") == "\\xF7\\x80\\x80\\x80"); } SECTION("Missing continuation byte(s)") { // Missing first continuation byte - CHECK(encode("\xDE") == u8"\\xDE"); - CHECK(encode("\xDF") == u8"\\xDF"); - CHECK(encode("\xE0") == u8"\\xE0"); - CHECK(encode("\xEF") == u8"\\xEF"); - CHECK(encode("\xF0") == u8"\\xF0"); - CHECK(encode("\xF4") == u8"\\xF4"); + CHECK(encode("\xDE") == "\\xDE"); + CHECK(encode("\xDF") == "\\xDF"); + CHECK(encode("\xE0") == "\\xE0"); + CHECK(encode("\xEF") == "\\xEF"); + CHECK(encode("\xF0") == "\\xF0"); + CHECK(encode("\xF4") == "\\xF4"); // Missing second continuation byte - CHECK(encode("\xE0\x80") == u8"\\xE0\\x80"); - CHECK(encode("\xE0\xBF") == u8"\\xE0\\xBF"); - CHECK(encode("\xE1\x80") == u8"\\xE1\\x80"); - CHECK(encode("\xF0\x80") == u8"\\xF0\\x80"); - CHECK(encode("\xF4\x80") == u8"\\xF4\\x80"); + CHECK(encode("\xE0\x80") == "\\xE0\\x80"); + CHECK(encode("\xE0\xBF") == "\\xE0\\xBF"); + CHECK(encode("\xE1\x80") == "\\xE1\\x80"); + CHECK(encode("\xF0\x80") == "\\xF0\\x80"); + CHECK(encode("\xF4\x80") == "\\xF4\\x80"); // Missing third continuation byte - CHECK(encode("\xF0\x80\x80") == u8"\\xF0\\x80\\x80"); - CHECK(encode("\xF4\x80\x80") == u8"\\xF4\\x80\\x80"); + CHECK(encode("\xF0\x80\x80") == "\\xF0\\x80\\x80"); + CHECK(encode("\xF4\x80\x80") == "\\xF4\\x80\\x80"); } } +#undef ESC } |